TEST(Reproducibility_GoogLeNet_fp16, Accuracy)
{
const float l1 = 1e-5;
const float lInf = 3e-3;
const string proto = findDataFile("dnn/bvlc_googlenet.prototxt", false);
const string model = findDataFile("dnn/bvlc_googlenet.caffemodel", false);
shrinkCaffeModel(model, "bvlc_googlenet.caffemodel_fp16");
Net net = readNetFromCaffe(proto, "bvlc_googlenet.caffemodel_fp16");
std::vector<Mat> inpMats;
inpMats.push_back( imread(_tf("googlenet_0.png")) );
inpMats.push_back( imread(_tf("googlenet_1.png")) );
ASSERT_TRUE(!inpMats[0].empty() && !inpMats[1].empty());
net.setInput(blobFromImages(inpMats, 1.0f, Size(), Scalar(), false), "data");
Mat out = net.forward("prob");
Mat ref = blobFromNPY(_tf("googlenet_prob.npy"));
normAssert(out, ref, "", l1, lInf);
}
// Test object detection network from Darknet framework.
void testDarknetModel(const std::string& cfg, const std::string& weights,
const std::vector<std::vector<int> >& refClassIds,
const std::vector<std::vector<float> >& refConfidences,
const std::vector<std::vector<Rect2d> >& refBoxes,
double scoreDiff, double iouDiff, float confThreshold = 0.24, float nmsThreshold = 0.4)
{
checkBackend();
Mat img1 = imread(_tf("dog416.png"));
Mat img2 = imread(_tf("street.png"));
std::vector<Mat> samples(2);
samples[0] = img1; samples[1] = img2;
// determine test type, whether batch or single img
int batch_size = refClassIds.size();
CV_Assert(batch_size == 1 || batch_size == 2);
samples.resize(batch_size);
Mat inp = blobFromImages(samples, 1.0/255, Size(416, 416), Scalar(), true, false);
Net net = readNet(findDataFile("dnn/" + cfg, false),
findDataFile("dnn/" + weights, false));
net.setPreferableBackend(backend);
net.setPreferableTarget(target);
net.setInput(inp);
std::vector<Mat> outs;
net.forward(outs, getOutputsNames(net));
for (int b = 0; b < batch_size; ++b)
{
std::vector<int> classIds;
std::vector<float> confidences;
std::vector<Rect2d> boxes;
for (int i = 0; i < outs.size(); ++i)
{
Mat out;
if (batch_size > 1){
// get the sample slice from 3D matrix (batch, box, classes+5)
Range ranges[3] = {Range(b, b+1), Range::all(), Range::all()};
out = outs[i](ranges).reshape(1, outs[i].size[1]);
}else{
out = outs[i];
}
for (int j = 0; j < out.rows; ++j)
{
Mat scores = out.row(j).colRange(5, out.cols);
double confidence;
Point maxLoc;
minMaxLoc(scores, 0, &confidence, 0, &maxLoc);
if (confidence > confThreshold) {
float* detection = out.ptr<float>(j);
double centerX = detection[0];
double centerY = detection[1];
double width = detection[2];
double height = detection[3];
boxes.push_back(Rect2d(centerX - 0.5 * width, centerY - 0.5 * height,
width, height));
confidences.push_back(confidence);
classIds.push_back(maxLoc.x);
}
}
}
// here we need NMS of boxes
std::vector<int> indices;
NMSBoxes(boxes, confidences, confThreshold, nmsThreshold, indices);
std::vector<int> nms_classIds;
std::vector<float> nms_confidences;
std::vector<Rect2d> nms_boxes;
for (size_t i = 0; i < indices.size(); ++i)
{
int idx = indices[i];
Rect2d box = boxes[idx];
float conf = confidences[idx];
int class_id = classIds[idx];
nms_boxes.push_back(box);
nms_confidences.push_back(conf);
nms_classIds.push_back(class_id);
}
normAssertDetections(refClassIds[b], refConfidences[b], refBoxes[b], nms_classIds,
nms_confidences, nms_boxes, format("batch size %d, sample %d\n", batch_size, b).c_str(), confThreshold, scoreDiff, iouDiff);
}
}
TEST_P(Test_ONNX_nets, Googlenet)
{
if (backend == DNN_BACKEND_INFERENCE_ENGINE)
throw SkipTestException("");
const String model = _tf("models/googlenet.onnx");
Net net = readNetFromONNX(model);
ASSERT_FALSE(net.empty());
net.setPreferableBackend(backend);
net.setPreferableTarget(target);
std::vector<Mat> images;
images.push_back( imread(_tf("../googlenet_0.png")) );
images.push_back( imread(_tf("../googlenet_1.png")) );
Mat inp = blobFromImages(images, 1.0f, Size(), Scalar(), false);
Mat ref = blobFromNPY(_tf("../googlenet_prob.npy"));
checkBackend(&inp, &ref);
net.setInput(inp);
ASSERT_FALSE(net.empty());
Mat out = net.forward();
normAssert(ref, out, "", default_l1, default_lInf);
expectNoFallbacksFromIE(net);
}
TEST_P(Reproducibility_MobileNet_SSD, Accuracy)
{
const string proto = findDataFile("dnn/MobileNetSSD_deploy.prototxt", false);
const string model = findDataFile("dnn/MobileNetSSD_deploy.caffemodel", false);
Net net = readNetFromCaffe(proto, model);
int targetId = GetParam();
const float l1 = (targetId == DNN_TARGET_OPENCL_FP16) ? 1.5e-4 : 1e-5;
const float lInf = (targetId == DNN_TARGET_OPENCL_FP16) ? 4e-4 : 1e-4;
net.setPreferableTarget(targetId);
Mat sample = imread(_tf("street.png"));
Mat inp = blobFromImage(sample, 1.0f / 127.5, Size(300, 300), Scalar(127.5, 127.5, 127.5), false);
net.setInput(inp);
Mat out = net.forward();
const float scores_diff = (targetId == DNN_TARGET_OPENCL_FP16) ? 4e-4 : 1e-5;
const float boxes_iou_diff = (targetId == DNN_TARGET_OPENCL_FP16) ? 5e-3 : 1e-4;
Mat ref = blobFromNPY(_tf("mobilenet_ssd_caffe_out.npy"));
normAssertDetections(ref, out, "", 0.0, scores_diff, boxes_iou_diff);
// Check that detections aren't preserved.
inp.setTo(0.0f);
net.setInput(inp);
out = net.forward();
out = out.reshape(1, out.total() / 7);
const int numDetections = out.rows;
ASSERT_NE(numDetections, 0);
for (int i = 0; i < numDetections; ++i)
{
float confidence = out.ptr<float>(i)[2];
ASSERT_EQ(confidence, 0);
}
// Check batching mode.
ref = ref.reshape(1, numDetections);
inp = blobFromImages(std::vector<Mat>(2, sample), 1.0f / 127.5, Size(300, 300), Scalar(127.5, 127.5, 127.5), false);
net.setInput(inp);
Mat outBatch = net.forward();
// Output blob has a shape 1x1x2Nx7 where N is a number of detection for
// a single sample in batch. The first numbers of detection vectors are batch id.
outBatch = outBatch.reshape(1, outBatch.total() / 7);
EXPECT_EQ(outBatch.rows, 2 * numDetections);
normAssert(outBatch.rowRange(0, numDetections), ref, "", l1, lInf);
normAssert(outBatch.rowRange(numDetections, 2 * numDetections).colRange(1, 7), ref.colRange(1, 7),
"", l1, lInf);
}